Research Methods in Psychology

Introduction to Psychological Research

• There are many popular sayings related to psychology (e.g., "Opposites attract").

• A key lesson in this class is to differentiate between folk psychology and scientific psychology.

• Psychological Myths: These are considered myths not necessarily because they are false, but because they lack positive evidence.

  • It's possible to find evidence for these myths or conditions under which they are true, at which point they would cease to be myths.

The Importance of Research Methods

• In science, how we know is just as important as what we know.

• A background in research methods allows one to ask and answer questions with greater precision.

• It is crucial to think critically about methods to become a smart consumer of science news.

• This course only provides a basic overview; more detailed exploration occurs in specialized classes like "Research Methods in Psychology and Statistics."

From Research Questions to Hypotheses

• All psychological scientists begin with a research question.

  • Examples: "How does creative thinking differ from logical thinking?" "Is the food you eat related to your mood?" "Do opposites attract?"

  • The number of possible research questions is infinite.

• These research questions inform theories.

  • Theory = An explanation using an integrated set of principles that organizes and predicts observations.

• From theories, scientists create hypotheses.

  • Hypothesis = A specific, testable prediction that refers to exactly what is being measured in a study.

• **Examples of Theories and Hypotheses: ** * Theory: Caffeine intake causes increased speed of mental functioning.

  • Hypothesis 1: Drinking a cup of black tea prior to taking a problem-solving test will increase the number of problems solved in 15 minutes (compared to not drinking tea).

  • Hypothesis 2: Drinking Red Bull before writing a paper will lead to a faster time in writing a paper (compared to not drinking Red Bull).

• Theory (broad, abstract) informs Hypothesis (specific, concrete).

• We all develop daily theories and hypotheses (acting as "armchair psychologists") to predict and manage our lives (e.g., hypothesizing that eating food decreases hunger).

• Scientists systematically make and test predictions because personal theories can often be incorrect.

Operational Definitions

• Before conducting a study, researchers must create operational definitions for their variables.

• Operational Definition = A statement of the concrete procedures (operations) used to define research variables, precisely explaining how hypotheses can be tested.

• **Examples: ** * Operational definition of "caffeine intake": Drinking 2 cups of coffee (200 mg of caffeine).

  • Operational definition of "speed of mental functioning": How fast one can solve a series of anagrams.

Relationships Between Variables: Correlations

• Correlations describe relationships between variables.

• Positive relationships (Positive Correlation): As a score on one variable increases, the score on a second variable tends to increase (e.g., X increases, Y increases).

• Negative relationships (Negative Correlation): As a score on one variable increases, the score on a second variable tends to decrease (e.g., X increases, Y decreases).

• No Correlation: No systematic relationship between variables.

• What correlations tell you: That two variables are related.

• What correlations do NOT tell you: How variables are related or about causality.

  • Third Variable Problem: An unmeasured third variable might be causing the observed correlation (e.g., ice cream sales and murders are correlated, but higher temperatures might cause both).

Causality

• Causality is concerned with whether one variable causes another variable (e.g., smoking causes lung cancer).

• Scientific theories are fundamentally interested in causality, regardless of how easily or directly it can be measured.

  • Smoking \Rightarrow Lung cancer

Research Study Designs

• Psychologists use various study designs:

  • Surveys

  • Experiments

  • Naturalistic observations

  • Case studies (less common)

• Experiments provide the clearest information about causality.

Understanding Experiments

• In an experiment, researchers manipulate one variable to observe its effects on another variable.

• The variable believed to be the cause is the one manipulated.

• Independent Variable (IV):

  • The variable that is manipulated by the experimenter.

  • It is the variable doing the causing.

  • In the caffeine study example, the IV is the amount of caffeine (e.g., none or some).

• Dependent Variable (DV):

  • The variable that is measured by the experimenter.

  • Its value depends in part on the independent variable; it is the variable being caused.

  • In the caffeine study example, the DV might be problem-solving speed or algebra-solving speed.

  • \text{IV} \Rightarrow \text{DV}

Building an Experiment (Caffeine and Mental Functioning Example)

• Scenario: Testing if coffee (caffeine) increases problem-solving speed.

• Groups:

  • Group A (Experimental Group): Receives coffee (treatment).

  • Group B (Control Group): Receives no coffee (baseline for comparison).

• Both groups take a problem-solving test.

• If the theory is correct, the experimental group should score higher.

Confounding Variables

• Confounding Variables = Any variables, other than the IV, that can serve as an alternative explanation for an observed effect.

  • Example: If coffee is given, perhaps the hot water in the coffee, not the caffeine, is causing increased mental functioning.

  • Caffeine \Rightarrow Increased mental functioning; Hot water \Rightarrow Increased mental functioning.

• Researchers aim to control for possible confounds.

  • To control for the hot water confound, one might give a control group hot water or, ideally, decaffeinated coffee.

  • The experimental group receives the treatment (e.g., caffeinated coffee).

  • The control group receives no treatment or a placebo (e.g., decaffeinated coffee) to provide a baseline.

Random Assignment

• Experiments must also address pre-existing differences between participants in groups.

• Random Assignment = A procedure where each participant has an equal chance of being assigned to any experimental condition (e.g., experimental group or control group).

  • Purpose: Helps ensure that groups are equal on average before the experimental manipulation is administered.

• If random assignment is effective, the groups should score similarly on the dependent variable before any intervention.

• Because random assignment assumes initial equality, researchers typically only need to measure the dependent variable after the manipulation.

• Any observed differences after the manipulation can then be attributed to the manipulation itself.

• Random assignment is a powerful tool for controlling for many potential confounding variables.

Understanding Data: Basic Statistics

• The goal is to provide general tools for thinking about data, rather than focusing on complex terminology or formulas (t-tests, f-tests, p values, beta values).

• Data is "Noisy":

  • A study provides a noisy measure, not the "true" result, due to:

    • Differences in people (individual variability).

    • Observation noise (measurement error).

    • Limited samples (experiments test a sample of people to make inferences about a larger population).

• Variation is Not Random: Many natural phenomena, including psychological data, often follow predictable patterns, such as the normal distribution (illustrated by a Plinko board).

Descriptive Statistics

• Measures of Central Tendency: Single scores that represent where data generally cluster.

  • Mode: The most frequently occurring score(s) in a distribution.

  • Mean: The arithmetic average of a distribution, calculated by adding all scores and dividing by the number of scores. It is the most common measure but can be distorted by outliers (atypical scores).

  • Median: The middle score in a distribution; half the scores are above it, and half are below it.

• In a normal distribution, the mean, median, and mode are located at the same point.

• In skewed distributions (e.g., hypothetical family income), the mean, median, and mode will differ.

• Measures of Dispersion (or Variation): Reveal the similarity or diversity of scores.

  • Range: The difference between the highest and lowest scores in a distribution.

  • Standard Deviation (SD): A computed measure of how much scores vary around the mean score.

    • A small standard deviation indicates scores are clustered closely around the mean.

    • A large standard deviation indicates scores are spread out widely from the mean.

Inferential Statistics

• "Statistical significance" refers to inferential statistics.

• For introductory purposes, inferential statistics are a way psychologists decide if an outcome is meaningful.

• They help determine if observed group differences in an experiment are statistically significant (i.e., unlikely to have occurred by chance).

• Statistical tests (in their simplest terms) measure the size of the difference relative to the amount of variance.

• Significance is most likely when:

  • Group differences are large.

  • Variance within groups is low.

  • The imaginary data in the lecture that showed stronger support for the hypothesis had larger mean differences and less overlap/variance between groups.

Factors Influencing Statistical Significance

• In an experiment comparing group differences, the significance of a result is influenced by:

  • 1)$ Size of the Difference: Larger differences between group means are more likely to be significant (all else being equal).

  • 2)$ Variability: Less random variability (lower standard deviation) within groups is more likely to lead to significant results (all else being equal).

  • $$3)$ Sample Size: More data points (larger sample size) are more likely to lead to significant results (all else being equal).

Learning Diary

• Questions for Critical Thinking:

  • What does it mean to think critically?

  • What previous experience do you have where you were asked to think critically?

  • Do you believe critical thinking is a skill developed over time or an innate ability?

  • What does it mean to be a critical consumer of knowledge and information?

  • Why is being a critical consumer a skill taught in an Introduction to Psychology course?